CN111620014A - Multilayer pallet identification and obstacle avoidance device and method for storage and transportation AGV - Google Patents
Multilayer pallet identification and obstacle avoidance device and method for storage and transportation AGV Download PDFInfo
- Publication number
- CN111620014A CN111620014A CN202010364783.7A CN202010364783A CN111620014A CN 111620014 A CN111620014 A CN 111620014A CN 202010364783 A CN202010364783 A CN 202010364783A CN 111620014 A CN111620014 A CN 111620014A
- Authority
- CN
- China
- Prior art keywords
- agv
- pallet
- module
- fork
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
- B65G1/02—Storage devices
- B65G1/04—Storage devices mechanical
- B65G1/0492—Storage devices mechanical with cars adapted to travel in storage aisles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G1/00—Storing articles, individually or in orderly arrangement, in warehouses or magazines
- B65G1/02—Storage devices
- B65G1/04—Storage devices mechanical
- B65G1/137—Storage devices mechanical with arrangements or automatic control means for selecting which articles are to be removed
- B65G1/1373—Storage devices mechanical with arrangements or automatic control means for selecting which articles are to be removed for fulfilling orders in warehouses
Abstract
The invention provides a device for identifying and avoiding barriers of a warehouse-transporting AGV (automatic guided vehicle) multilayer pallet, which comprises embedded AI computing equipment, a binocular vision module, a positioning navigation module, a driving control module and a management monitoring scheduling module, wherein the binocular vision module is used for carrying out real-time classification identification and distance measurement on pallet fork holes, personnel, vehicles, idle loading and unloading areas and obstacles and judging whether the fork entering direction is accurate or not; the positioning navigation module is used for realizing the autonomous navigation and obstacle avoidance functions of the AGV; the driving control module is used for controlling the driving motor to drive the AGV to run and the fork rod to move; the management monitoring scheduling module is used for realizing the acquisition and release of tasks, path planning and the monitoring and management of vehicles, goods and personnel; the embedded AI computing device is used to confirm the number of shelves on which the pallet is located. The pallet on the multi-layer goods shelf can be accurately identified and accurately picked, and obstacles such as personnel, vehicles and the like and non-working areas can be timely avoided.
Description
Technical Field
The invention belongs to the technology of storage and transportation AGV, and particularly relates to an AVG multi-layer pallet identification and obstacle avoidance device and method for storage and transportation.
Background
In modern factory warehouse logistics, forklifts play an important role in large material handling and small cargo transportation. At present, storage and transportation AGVs with technologies such as intelligent identification, autonomous positioning navigation, and high-speed information transmission are being developed vigorously. Usually, the goods to be transported are loaded on the pallet, two square fork holes are formed in the side face of the pallet, and when the AGV carries the goods in the warehouse, the AGV carries the goods by recognizing the positions of the fork holes of the pallet.
However, in the actual factory storage environment, different model pallets that different mills used, its fork hole outward appearance, shape are different, and the pallet is not put in the position accuracy, and numerous pallets are intensive on every side and are put the circumstances such as, lead to carrying the unable accurate discernment pallet fork hole of AGV in the storage, and the factory environment is complicated simultaneously, and personnel walk at will, and the vehicle traveles at will, has aggravated the potential safety hazard greatly for the unable accuracy of storage transport AGV and safety carry the goods.
Disclosure of Invention
The invention aims to provide an AVG multilayer pallet identifying and obstacle avoiding device for storage and transportation.
The technical solution for realizing the purpose of the invention is as follows: a multi-layer pallet recognition and obstacle avoidance device for a storage and transportation AGV comprises an embedded AI computing device, a binocular vision module, a positioning navigation module, a driving control module and a management monitoring scheduling module, wherein,
the binocular vision module is used for carrying out real-time classification recognition and distance measurement on pallet fork holes, personnel, vehicles, idle goods loading and unloading areas and obstacles and judging whether the fork entering direction is accurate or not;
the positioning navigation module is used for realizing the autonomous navigation and obstacle avoidance functions of the AGV;
the driving control module is used for controlling the driving motor to drive the AGV to run and the fork rod to move;
the management monitoring and scheduling module is used for realizing the acquisition and the release of tasks, the path planning and the monitoring and the management of vehicles, goods and personnel;
the embedded AI computing device is used to confirm the number of shelves on which the pallet is located.
A multilayer pallet identification and obstacle avoidance method for a storage and transportation AGV comprises the following steps:
step 1, according to task information issued by a management monitoring scheduling module, a driving control module controls a warehousing and transportation AGV to stop at the position 5m in front of a loading and unloading area;
step 2, identifying and ranging the cargo loading and unloading area through a binocular vision module, and identifying and ranging pallet fork holes;
step 3, adjusting the posture of the vehicle body in real time through a driving control module to enter the fork according to the pallet fork hole identification and distance measurement information;
step 4, detecting information of the personnel, the vehicle and the obstacle in real time and avoiding obstacles through the binocular vision module and the positioning navigation module in the process of entering the fork;
and 5, when the storage transport AGV travels 2m away from the pallet, the embedded AI computing equipment confirms the number of layers of the shelf where the pallet is located, and the drive control module controls the lifting fork rod to complete fork entering.
Compared with the prior art, the invention has the following remarkable advantages: 1) the invention improves the fork inserting accuracy of the warehousing and transporting AGV to the pallet jacks on the multilayer goods shelf in the fork inserting process; 2) the invention realizes the intelligent work of the AGV forklift and improves the operation efficiency and safety of a factory; 3) the invention has good working capacity under complex environments such as factories, warehouses and the like, and can adapt to all-weather work.
The present invention is described in further detail below with reference to the attached drawings.
Drawings
Fig. 1 is a schematic structural diagram of an AGV pallet recognition and obstacle avoidance device for storage and transportation.
FIG. 2 is a flow chart of a method for identifying and avoiding obstacles in a storage AGV.
Detailed Description
As shown in fig. 1, the multilayer pallet recognition and obstacle avoidance device for storage and transportation AGVs comprises an embedded AI computing device 10, a binocular vision module 11, a positioning navigation module 12, a driving control module 13 and a management monitoring scheduling module 14;
embedded AI computing equipment 10 is provided with dual-core Denver 264 position CPU and four-core ARM A57 complete, the GPU of 256 NVIDIA CUDA cores, the hard disk, the WIFI module, gigabit Ethernet module, bluetooth module, video input/output HDMI interface module, several data bus I2C interface module, several data bus CAN interface module, several data bus SPI interface module, several data bus UART interface module, several USB3.0 interface module, several sound module, the bright LED warning light of several height, liquid crystal display. The hard disk of the equipment is loaded with a control program, so that automatic operation and artificial intelligence of AGV storage and transportation are achieved.
The binocular vision module 11 is provided with a binocular camera with the resolution of 2560 x 960 (binocular), a 3.9mm distortion-free lens, an ambient light detector, a high-brightness LED lamp, a video output MJPEG format, a frame rate of 90fps, a USB3.0 interface, a working voltage DV5V and a working current of 160mA, is matched with a Caffe-SSD deep learning network program to perform identification and an SGBM binocular matching distance measurement algorithm program to perform distance measurement, and is used for real-time classification identification and distance measurement of pallet fork holes, personnel, vehicles, idle loading and unloading areas, obstacles and the like.
The positioning navigation module 12 comprises a plurality of UWB positioning base stations arranged in a factory area, a vehicle-mounted UWB positioning label module for warehousing and transporting AGV, a UWB positioning label module carried by a worker, and a vehicle-mounted UWB positioning label module for other working vehicles. The system is used for positioning the storage and transportation AGV, workers and other working vehicles in real time, navigating the AGV through the positioning information and avoiding obstacles for the workers, other working vehicles and non-working areas.
The driving control module 13 controls the driving motors for driving the storage AGV and controlling the fork rods to move, so that the functions of driving the storage AGV and forking the pallet are achieved.
The management monitoring and scheduling module 14 is installed on a remote computer, and includes an information acquisition system, a vehicle scheduling system, a video monitoring system, a path planning system, and the like, and implements functions of acquiring and issuing tasks, path planning, monitoring and managing vehicles, goods, and personnel, and the like.
Therefore, the problems that the recognition rate of the storage and transportation AGV pallets is low, the fork rods cannot be accurately inserted into the pallets, huge potential safety hazards exist and the like are solved, the pallets on the multilayer goods shelf can be accurately recognized and accurately picked, and people, vehicles and obstacles are timely prevented from being obstructed, so that the intelligent work of the storage and transportation AGV is realized, and the operation efficiency and the safety of a factory are improved.
With reference to fig. 1-2, the method for identifying and avoiding the obstacle of the AGV multi-layer pallet conveyed in the warehouse comprises the following steps:
step 1, according to task information issued by a management monitoring scheduling module 14, a driving control module 13 controls a warehousing and transportation AGV to stop at the position 5m in front of a loading and unloading area;
step 2, identifying and ranging the cargo handling area through the binocular vision module 11, and identifying and ranging pallet fork holes;
step 3, adjusting the posture of the vehicle body in real time through a driving control module 13 according to the pallet fork hole identification and distance measurement information to enter the fork;
step 4, in the process of entering into the fork, detecting information of the personnel, the vehicles and the obstacles in real time through the binocular vision module 11 and the positioning navigation module 12 and avoiding obstacles;
and 5, when the warehousing and transportation AGV travels 2m away from the pallet, the embedded AI computing equipment 10 confirms the number of layers of the shelf where the pallet is located, and the driving control module 13 controls the lifting fork rod to complete fork entering.
Further, in step 1, according to the task information issued by the management monitoring scheduling module 14, the driving control module 13 controls the storage transporting AGVs to stop at the front 5m of the loading and unloading area, as shown in fig. 1-2, specifically:
step 1-1, the warehousing and transportation AGV acquires task information including coordinate information of a loading and unloading area, path planning information, information of the number of layers of pallets, goods information and the like issued by the management monitoring module 14, and replies the AGV number, the current state and the execution condition to the management monitoring module 14;
step 1-2, the positioning navigation module 12 determines an AGV driving route according to the path planning information, and the driving control module 13 controls the AGV to drive to the position 5m before the loading and unloading area;
step 1-3, the positioning navigation module 12 and the binocular vision module 11 detect whether personnel exist or not and whether vehicles are between a loading and unloading area and an AGV in real time in the driving process, if so, obstacle avoidance is carried out, sound and light alarm is carried out, and alarm information is transmitted to the management monitoring and scheduling module.
Further, step 2 the storage and transportation AGV identifies and measures the loading and unloading area through the binocular vision module 11, identifies and measures the pallet fork holes, specifically as shown in fig. 1-2:
step 2-1, detecting the current ambient light intensity by an ambient light detector on the binocular vision module 11, and turning on a high-brightness LED lamp if the ambient light intensity is too low;
2-2, identifying and ranging a loading and unloading area by the warehousing and transportation AGV through the binocular vision module 11, if no pallet is detected in the loading and unloading area, performing sound-light alarm, and transmitting alarm information to the management monitoring and scheduling module 14;
2-3, identifying and ranging pallet fork holes by the warehousing and transportation AGV through the binocular vision module 11, if the pallet fork hole position identification and the distance measurement fail, performing sound-light alarm, and transmitting alarm information to the management monitoring and scheduling module 14;
further, step 3 the storage and transportation AGV adjusts the posture of the car body in real time through the driving control module 13 according to the pallet fork hole identification and distance measurement information, and specifically, as shown in fig. 1-2:
3-1, adjusting the posture of the car body by the storage and transportation AGV through a driving control module 13 according to the pallet fork hole identification and distance measurement information;
3-2, if one of the eyes A of the binocular vision module 11 identifies the pallet and the other eye B does not identify the pallet, driving the control module 13 to slowly adjust the posture of the body in the direction of the identified eye A of the pallet until both eyes identify the pallet;
3-3, taking the average distance measurement of every 10 frames of video information acquired by the binocular vision module 11 as a standard for the current pallet fork hole distance, and when the measurement distance of one eye A of the binocular vision module 11 is higher than that of the other eye B, driving the control module to slowly adjust the posture of the vehicle body in the direction of the eye A with the higher measurement distance until the binocular measurement distances are almost consistent;
3-4, when the distance phase difference between the left visual measurement and the right visual measurement of the binocular vision module 11 is smaller than 1cm, the driving control module 13 starts to control the AGV to slowly enter the fork;
further, in the fork entering process in step 4, the storage and transportation AGV intelligently detects target information such as people, vehicles, obstacles and the like in real time through the binocular vision module 11 and the positioning navigation module 12 and carries out obstacle avoidance, which specifically includes:
and 4-1, in the fork entering process, identifying the storage and transportation AGV in real time through the binocular vision module 11, stopping immediately and giving sound and light alarm if vehicles, personnel, obstacles and the like are detected to be present in the 5m range of the AGV body in the current operation, and transmitting alarm information to the management monitoring and dispatching module 14 in real time.
And 4-2, detecting coordinate information of a worker, other working vehicles and the like by the storage and transportation AGV through the positioning navigation module 12, stopping immediately and giving an audible and visual alarm if the coordinate information is detected to be within the working range of the current operation AGV, and transmitting the alarm information to the management monitoring and dispatching module 14 in real time.
Further, in step 5, when the warehousing and transportation AGV travels 2m away from the pallet, the embedded AI computing device 10 determines the number of shelf layers where the pallet is located, and the driving control module 13 controls the lifting fork rod to complete fork entry, as shown in fig. 1-2, specifically:
step 5-1, when the warehousing and transportation AGV travels 2m away from the pallet, the embedded AI computing equipment 10 matches the information of the number of layers of the pallet contained in the task information with the position information of the pallet jack identified by the binocular vision module 11, confirms the number of layers of the shelf where the pallet is located, stops the vehicle immediately and gives an audible and visual alarm if the number of layers of the shelf where the pallet is located is detected to be unmatched, and transmits alarm information to the management monitoring and scheduling module in real time;
step 5-2, the driving control module 13 controls lifting of the jack arm according to the height of the layer number of the pallet;
step 5-3, the driving control module 13 controls the AGV to continue to advance, the fork entering condition is monitored in real time through the binocular vision module 11, if the fact that the fork rod does not enter the fork correctly or the pallet is about to collide is recognized, the AGV is withdrawn immediately, and the posture of the vehicle body is adjusted again;
and 5-4, controlling the AGV to continue to complete fork entry by the driving control module 13, and transmitting task completion information to the management monitoring scheduling module 14 by the warehousing and transporting AGV.
Claims (7)
1. A multi-layer pallet recognition and obstacle avoidance device for a storage and transportation AGV is characterized by comprising an embedded AI computing device, a binocular vision module, a positioning navigation module, a driving control module and a management monitoring scheduling module, wherein,
the binocular vision module is used for carrying out real-time classification recognition and distance measurement on pallet fork holes, personnel, vehicles, idle goods loading and unloading areas and obstacles and judging whether the fork entering direction is accurate or not;
the positioning navigation module is used for realizing the autonomous navigation and obstacle avoidance functions of the AGV;
the driving control module is used for controlling the driving motor to drive the AGV to run and the fork rod to move;
the management monitoring and scheduling module is used for realizing the acquisition and the release of tasks, the path planning and the monitoring and the management of vehicles, goods and personnel;
the embedded AI computing device is used to confirm the number of shelves on which the pallet is located.
2. A multilayer pallet identification and obstacle avoidance method for a storage and transportation AGV is characterized by comprising the following steps:
step 1, according to task information issued by a management monitoring scheduling module, a driving control module controls a warehousing and transportation AGV to stop at the position 5m in front of a loading and unloading area;
step 2, identifying and ranging the cargo loading and unloading area through a binocular vision module, and identifying and ranging pallet fork holes;
step 3, adjusting the posture of the vehicle body in real time through a driving control module to enter the fork according to the pallet fork hole identification and distance measurement information;
step 4, detecting information of the personnel, the vehicle and the obstacle in real time and avoiding obstacles through the binocular vision module and the positioning navigation module in the process of entering the fork;
and 5, when the storage transport AGV travels 2m away from the pallet, the embedded AI computing equipment confirms the number of layers of the shelf where the pallet is located, and the drive control module controls the lifting fork rod to complete fork entering.
3. The AGV multilayer pallet identification and obstacle avoidance method according to claim 2, wherein the specific method of driving the control module to stop at 5m in front of the loading and unloading area according to the task information issued by the management monitoring and scheduling module in step 1 is as follows:
step 1-1, a warehousing and transportation AGV acquires task information including coordinate information of a loading and unloading area, path planning information, information of the number of layers where pallets are located, cargo information and the like, which is issued by a management monitoring module, and replies the AGV number, the current state and the execution condition to the management monitoring module;
step 1-2, the positioning navigation module determines an AGV driving route according to the path planning information, and the driving control module controls the AGV to drive to the position 5m before the loading and unloading area;
and 1-3, detecting whether personnel exist or not and whether the vehicle is between a loading and unloading area and the AGV in real time in the driving process by the positioning navigation module and the binocular vision module, if so, avoiding obstacles, giving an audible and visual alarm, and transmitting the alarm information to the management monitoring and scheduling module.
4. The AGV multilayer pallet identification and obstacle avoidance method according to claim 2, wherein in step 2, the AGV identifies and measures the loading and unloading area through the binocular vision module, and the specific method for identifying and measuring the pallet fork holes comprises the following steps:
step 2-1, detecting the current ambient light intensity by an ambient light detector on a binocular vision module, and turning on a high-brightness LED lamp when the ambient light intensity is lower than a brightness threshold value;
2-2, identifying and ranging a loading and unloading area by the storage and transportation AGV through a binocular vision module, and when detecting that no pallet is in the loading and unloading area, performing sound-light alarm and transmitting alarm information to a management monitoring and dispatching module;
and 2-3, identifying and ranging pallet fork holes by the storage and transportation AGV through a binocular vision module, and when the positions of the pallet fork holes are identified and the distance is measured, performing sound-light alarm and transmitting alarm information to the management monitoring and scheduling module.
5. The AGV multilayer pallet recognition and obstacle avoidance method according to claim 2, wherein the specific method for the AGV to adjust the body posture into the fork in real time through the driving control module according to the pallet fork hole recognition and distance measurement information in step 3 is as follows:
3-1, adjusting the posture of the car body by the storage and transportation AGV through a driving control module according to pallet fork hole identification and distance measurement information;
3-2, if one of the eyes A of the binocular vision module identifies the pallet and the other eye B does not identify the pallet, driving the control module to adjust the posture of the body in the direction of the identified eye A of the pallet until both eyes identify the pallet;
3-3, taking the average distance measurement of every 10 frames of video information acquired by the binocular vision module as a standard for the current pallet fork hole distance, and when the measurement distance of one eye A of the binocular vision module is higher than that of the other eye B, driving the control module to slowly adjust the posture of the vehicle body in the direction of the eye A with the higher measurement distance until the binocular measurement distances are consistent;
and 3-4, when the distance phase difference between the left visual measurement and the right visual measurement of the binocular vision module is smaller than 1cm, the driving control module starts to control the AGV to enter the fork.
6. The AGV multilayer pallet identification and obstacle avoidance method according to claim 2, wherein in the fork entering process in step 4, the AGV real-time intelligent detection of target information such as personnel, vehicles, obstacles and the like through the binocular vision module and the positioning navigation module and the specific method for avoiding obstacles are as follows:
step 4-1, in the fork entering process, the storage and transportation AGV recognizes in real time through a binocular vision module, if a vehicle, a person, an obstacle and the like are detected to be within 5m of the current operation AGV body, the AGV stops immediately, performs sound and light alarm, and transmits alarm information to a management monitoring and dispatching module in real time;
and 4-2, detecting coordinate information of workers and other working vehicles by the storage and transportation AGV through the positioning navigation module, stopping immediately and giving an audible and visual alarm if the coordinate information is detected to be within the working range of the current operation AGV, and transmitting the alarm information to the management monitoring and dispatching module in real time.
7. The AGV multilayer pallet identification and obstacle avoidance method according to claim 2, wherein in step 5, when the AGV travels 2m away from the pallet, the embedded AI computing device determines the number of layers of the pallet where the pallet is located, and the specific method for controlling the lifting fork rod to complete fork entering by the driving control module is as follows:
step 5-1, when the storage and transportation AGV travels 2m away from the pallet, the embedded AI computing equipment matches the information of the number of layers of the pallet contained in the task information with the position information of the pallet jack identified by the binocular vision module, confirms the number of layers of the shelf where the pallet is located, stops the vehicle immediately and gives an audible and visual alarm if the number of layers of the shelf where the pallet is located is detected to be unmatched, and transmits alarm information to the management monitoring and scheduling module in real time;
step 5-2, the driving control module controls lifting of the jack arm according to the height of the layer number of the pallet;
5-3, controlling the AGV to continue to advance by the driving control module, monitoring the fork entering condition in real time through the binocular vision module, and if the fact that the fork rod does not enter the fork correctly or the pallet is about to collide is recognized, immediately withdrawing the AGV and readjusting the posture of the vehicle body;
and 5-4, controlling the AGV to continue to complete fork entry by the driving control module, and transmitting task completion information to the management monitoring scheduling module by the warehousing and transporting AGV.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010364783.7A CN111620014A (en) | 2020-04-30 | 2020-04-30 | Multilayer pallet identification and obstacle avoidance device and method for storage and transportation AGV |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010364783.7A CN111620014A (en) | 2020-04-30 | 2020-04-30 | Multilayer pallet identification and obstacle avoidance device and method for storage and transportation AGV |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111620014A true CN111620014A (en) | 2020-09-04 |
Family
ID=72268055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010364783.7A Pending CN111620014A (en) | 2020-04-30 | 2020-04-30 | Multilayer pallet identification and obstacle avoidance device and method for storage and transportation AGV |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111620014A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112340339A (en) * | 2020-11-09 | 2021-02-09 | 苏州罗伯特木牛流马物流技术有限公司 | Control system and method for accurately placing roadway for fork type AGV (automatic guided vehicle) carrying shuttle car |
| CN112875578A (en) * | 2020-12-28 | 2021-06-01 | 深圳市易艾得尔智慧科技有限公司 | Unmanned forklift control system |
| CN113703460A (en) * | 2021-08-31 | 2021-11-26 | 上海木蚁机器人科技有限公司 | Method, device and system for identifying vacancy of navigation vehicle |
| CN114428503A (en) * | 2021-12-28 | 2022-05-03 | 深圳优地科技有限公司 | Material carrying method and device, intelligent equipment and storage medium |
| CN114524209A (en) * | 2021-12-21 | 2022-05-24 | 杭叉集团股份有限公司 | AGV high-position stacking method and detection device based on double TOF cameras |
| CN117093009A (en) * | 2023-10-19 | 2023-11-21 | 湖南睿图智能科技有限公司 | Logistics AGV trolley navigation control method and system based on machine vision |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5957898A (en) * | 1982-09-28 | 1984-04-03 | 株式会社豊田自動織機製作所 | Method of controlling cargo work in unmanned forklift |
| CN104777835A (en) * | 2015-03-11 | 2015-07-15 | 武汉汉迪机器人科技有限公司 | Omni-directional automatic forklift and 3D stereoscopic vision navigating and positioning method |
| CN105480903A (en) * | 2015-11-13 | 2016-04-13 | 上海诺力智能科技有限公司 | Positioning method of pallet fork |
| CN105480902A (en) * | 2016-01-19 | 2016-04-13 | 杭州瓦瑞科技有限公司 | Universal forklift type AGV |
| CN106672859A (en) * | 2017-01-05 | 2017-05-17 | 深圳市有光图像科技有限公司 | Method for visually identifying tray based on forklift and forklift |
| JP2018002335A (en) * | 2016-06-28 | 2018-01-11 | 三菱ロジスネクスト株式会社 | Forklift |
| CN108584809A (en) * | 2018-06-01 | 2018-09-28 | 上海诺力智能科技有限公司 | AGV fork trucks automatic access goods control system and method |
| CN109160452A (en) * | 2018-10-23 | 2019-01-08 | 西安中科光电精密工程有限公司 | Unmanned transhipment fork truck and air navigation aid based on laser positioning and stereoscopic vision |
| CN109323696A (en) * | 2018-11-07 | 2019-02-12 | 航天信息股份有限公司 | A kind of unmanned fork lift indoor positioning navigation system and air navigation aid |
| CN110054116A (en) * | 2019-03-15 | 2019-07-26 | 广州蓝胖子机器人有限公司 | Pallet fork air navigation aid, system and unmanned fork lift applied to fork truck |
| CN110182514A (en) * | 2019-05-14 | 2019-08-30 | 盐城品迅智能科技服务有限公司 | A kind of intelligent material conveying equipment Automatic Track Finding guiding vehicle and autonomous tracing in intelligent vehicle |
-
2020
- 2020-04-30 CN CN202010364783.7A patent/CN111620014A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5957898A (en) * | 1982-09-28 | 1984-04-03 | 株式会社豊田自動織機製作所 | Method of controlling cargo work in unmanned forklift |
| CN104777835A (en) * | 2015-03-11 | 2015-07-15 | 武汉汉迪机器人科技有限公司 | Omni-directional automatic forklift and 3D stereoscopic vision navigating and positioning method |
| CN105480903A (en) * | 2015-11-13 | 2016-04-13 | 上海诺力智能科技有限公司 | Positioning method of pallet fork |
| CN105480902A (en) * | 2016-01-19 | 2016-04-13 | 杭州瓦瑞科技有限公司 | Universal forklift type AGV |
| JP2018002335A (en) * | 2016-06-28 | 2018-01-11 | 三菱ロジスネクスト株式会社 | Forklift |
| CN106672859A (en) * | 2017-01-05 | 2017-05-17 | 深圳市有光图像科技有限公司 | Method for visually identifying tray based on forklift and forklift |
| CN108584809A (en) * | 2018-06-01 | 2018-09-28 | 上海诺力智能科技有限公司 | AGV fork trucks automatic access goods control system and method |
| CN109160452A (en) * | 2018-10-23 | 2019-01-08 | 西安中科光电精密工程有限公司 | Unmanned transhipment fork truck and air navigation aid based on laser positioning and stereoscopic vision |
| CN109323696A (en) * | 2018-11-07 | 2019-02-12 | 航天信息股份有限公司 | A kind of unmanned fork lift indoor positioning navigation system and air navigation aid |
| CN110054116A (en) * | 2019-03-15 | 2019-07-26 | 广州蓝胖子机器人有限公司 | Pallet fork air navigation aid, system and unmanned fork lift applied to fork truck |
| CN110182514A (en) * | 2019-05-14 | 2019-08-30 | 盐城品迅智能科技服务有限公司 | A kind of intelligent material conveying equipment Automatic Track Finding guiding vehicle and autonomous tracing in intelligent vehicle |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112340339A (en) * | 2020-11-09 | 2021-02-09 | 苏州罗伯特木牛流马物流技术有限公司 | Control system and method for accurately placing roadway for fork type AGV (automatic guided vehicle) carrying shuttle car |
| CN112875578A (en) * | 2020-12-28 | 2021-06-01 | 深圳市易艾得尔智慧科技有限公司 | Unmanned forklift control system |
| CN113703460A (en) * | 2021-08-31 | 2021-11-26 | 上海木蚁机器人科技有限公司 | Method, device and system for identifying vacancy of navigation vehicle |
| CN113703460B (en) * | 2021-08-31 | 2024-02-09 | 上海木蚁机器人科技有限公司 | Method, device and system for identifying vacant position of navigation vehicle |
| CN114524209A (en) * | 2021-12-21 | 2022-05-24 | 杭叉集团股份有限公司 | AGV high-position stacking method and detection device based on double TOF cameras |
| CN114428503A (en) * | 2021-12-28 | 2022-05-03 | 深圳优地科技有限公司 | Material carrying method and device, intelligent equipment and storage medium |
| CN117093009A (en) * | 2023-10-19 | 2023-11-21 | 湖南睿图智能科技有限公司 | Logistics AGV trolley navigation control method and system based on machine vision |
| CN117093009B (en) * | 2023-10-19 | 2024-02-09 | 湖南睿图智能科技有限公司 | Logistics AGV trolley navigation control method and system based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111620014A (en) | Multilayer pallet identification and obstacle avoidance device and method for storage and transportation AGV | |
| US11892853B2 (en) | Vehicle guidance systems and associated methods of use at logistics yards and other locations | |
| EP2542496B1 (en) | Method and system for sensing object load engagement and disengagement by automated vehicles | |
| CN109809334B (en) | Method for moving forklift to operate and lift | |
| CN102707718B (en) | Automatic guidance system controls the communication means of industrial vehicle | |
| CN109144068B (en) | Electric control method and control device for AGV fork truck with three-way forward moving type navigation switching function | |
| CN111027912B (en) | AGV inventory warehouse tray checking method based on RFID technology | |
| CN109704237B (en) | AGV pulls fork truck with intelligence is judged discernment perception function | |
| CN107145149A (en) | A kind of bridge type vehicle-driving device and its avoidance traveling method | |
| CN115826576A (en) | Intelligent control system and method for self-loading and unloading forklift robot | |
| KR20230173085A (en) | Smart warehouse safety mechanism | |
| CN115759892A (en) | Unmanned intelligent checking system and method for electric power material storage | |
| Cui et al. | Design of a novel AGV with automatic pick-and-place system based on scissor lifting platform | |
| JP7112803B1 (en) | Transport system and transport control method | |
| CN109947095A (en) | A kind of warehouse transfer robot | |
| CN112172959B (en) | Outdoor robot | |
| US11960299B2 (en) | System for autonomous and semi-autonomous material handling in an outdoor yard | |
| CN211366846U (en) | AGV (automatic guided vehicle) for storage and transportation | |
| CN218174564U (en) | Path optimization anti-collision recognition system for AGV trolley | |
| US20240017976A1 (en) | Advanced material handling vehicle | |
| CN219906883U (en) | Fork goods equipment | |
| US11802948B2 (en) | Industrial vehicle distance and range measurement device calibration | |
| US20220009759A1 (en) | Industrial vehicle distance and range measurement device calibration | |
| CN216266078U (en) | Warehouse inspection and checking integrated robot and system | |
| Simon et al. | 3D camera augmented Autonomous Mobile Robot for intralogistics purposes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200904 |